NVIDIA GeForce GTX 1650 SUPER vs NVIDIA H100 CNX

GPU Specs Compare

G

NVIDIA H100 CNX

NVIDIA 2023-03

Graphics Card

Release Date
Nov 2019
Mar 2023
Generation
GeForce 16
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16

Clock Speeds

Base Clock
1530 MHz
690 MHz
Boost Clock
1725 MHz
1845 MHz
Memory Clock
1500 MHz
1593 MHz

Memory

Memory Size
4GB
80GB
Memory Type
GDDR6
HBM2e
Memory Bus
128bit
5120bit
Bandwidth
192.0GB/s
2039GB/s

Render Config

SM Count
20
114
Shading Units
1280
14592
TMUs
80
456
ROPs
32
24
L1 Cache
64 KB (per SM)
256 KB (per SM)
L2 Cache
1024 KB
50 MB
Tensor Cores
-
456

Theoretical Performance

Pixel Rate
55.20 GPixel/s
44.28 GPixel/s
Texture Rate
138.0 GTexel/s
841.3 GTexel/s
FP16 (half)
8.832 TFLOPS
215.4 TFLOPS
FP32 (float)
4.416 TFLOPS
53.84 TFLOPS
FP64 (double)
138.0 GFLOPS
26.92 TFLOPS

Graphics Processor

GPU Name
TU116
GH100
GPU Variant
TU116-250-KA-A1
-
Architecture
Turing
Hopper
Foundry
TSMC
TSMC
Process Size
12 nm
4 nm
Transistors
6.6 billion
80 billion
Die Size
284 mm²
814 mm²

Board Design

TDP
100W
350W
Suggested PSU
300 W
750 W
Outputs
1x DVI1x HDMI 2.01x DisplayPort 1.4a
No outputs
Power Connectors
1x 6-pin
8-pin EPS

Graphics Features

DirectX
12 (12_1)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
7.5
9.0
Shader Model
6.6
N/A